itsdm calls isolation forest and variations such as
SCiForest and EIF to model species distribution. It provides features
including:
- A few functions to download environmental variables.
- Outlier tree-based suspicious environmental outliers detection.
- Isolation forest-based environmental suitability modeling.
- Non-spatial response curves of environmental variables.
- Spatial response maps of environmental variables.
- Variable importance analysis.
- Presence-only model evaluation.
- Method to convert predicted suitability to presence-absence
map.
- Variable contribution analysis for the target observations.
- Method to analyze the spatial impacts of changing environment.
To install the latest release on CRAN:
install.packages("itsdm")
The latest development
version on GitHub can be installed with:
# install.packages("remotes")
remotes::install_github("LLeiSong/itsdm")

This is a package that combines R and Python to do land cover
mapping. There are three main parts of scripts for this project:
- data_preprocess: this directory includes all scripts to download and
preprocess satellite images.
- guess_model: this directory includes all scripts to build
gap-filling Random Forest model and generate ensemble labels.
- hrlcm: this directory includes all scripts to build U-Net model to
do land cover mapping.
and other useful scripts and resources:
- tools: other useful scripts for post-mapping processing or use AWS
cloud computing.
- docs: useful tutorials or posters/presentations for conference.
![]()